Cognitive Robot Autonomy and Learning (CoRAL) Lab Seeking Students for Research Projects - Department of Computer Science - Purdue University Skip to main content

Cognitive Robot Autonomy and Learning (CoRAL) Lab Seeking Students for Research Projects

The Cognitive Robot Autonomy and Learning (CoRAL)lab in the Purdue CS Department is looking for undergraduate and graduate student volunteers to participate in various robotics and reinforcement learning research projects. Students will have the option to choose individual study credits or a thesis option. The projects are listed as follows:

 

Project #1: Persistent safety in reinforcement learning for robotics

Description: This project will investigate persistent safety in reinforcement learning for robotic applications. The main goal is to guarantee safety during training.

Desired background:

  • Must: Strong programming skills (Python) and experience training Deep Learning models.
  • Preference will be given to students with prior experience in Robotics and Reinforcement Learning.

[1] Ganai, Milan, et al. "Iterative reachability estimation for safe reinforcement learning." Advances in Neural Information Processing Systems 36 (2024).

[2] Yu, Dongjie, et al. "Reachability constrained reinforcement learning." International conference on machine learning. PMLR, 2022.

 

Project #2: Visual generalization for Imitation and Reinforcement Learning from pixels

Description: This project will investigate visual generalization for Imitation and Reinforcement Learning from pixels.

Desired background:

  • Must: Strong programming skills (Python) and experience training Deep Learning models.
  • Preference will be given to students with prior experience in Computer Vision, Imitation, and Reinforcement Learning.

[1] Yuan, Zhecheng, et al. "Rl-vigen: A reinforcement learning benchmark for visual generalization." Advances in Neural Information Processing Systems 36 (2024).

[2] Giammarino, Vittorio, James Queeney, and Ioannis Ch Paschalidis. "Visually robust adversarial imitation learning from videos with contrastive learning." arXiv preprint arXiv:2407.12792 (2024).

[3] Giammarino, Vittorio, James Queeney, and Ioannis Paschalidis. "Adversarial Imitation Learning from Visual Observations using Latent Information." Transactions on Machine Learning Research.

 

Project # 3: Spectral Decomposition Representation Learning for Imitation from videos

Description: This project will investigate the use of the MDP spectral decomposition for representation learning in adversarial imitation learning from videos.

Desired background:

  • Must: Strong programming skills (Python) and experience training Deep Learning models.
  • Preference will be given to students with prior experience with low-rank MDPs, Adversarial Imitation Learning and Reinforcement Learning.

[1] Efroni, Yonathan, et al. "Provable reinforcement learning with a short-term memory." International Conference on Machine Learning. PMLR, 2022.

[2] Guo, Jiacheng, et al. "Provably efficient representation learning with tractable planning in low-rank pomdp." International Conference on Machine Learning. PMLR, 2023.

[3] Ren, Tongzheng, et al. "Spectral Decomposition Representation for Reinforcement Learning." The Eleventh International Conference on Learning Representations.

[4] Giammarino, Vittorio, James Queeney, and Ioannis Ch Paschalidis. "Visually robust adversarial imitation learning from videos with contrastive learning." arXiv preprint arXiv:2407.12792 (2024).

[5] Giammarino, Vittorio, James Queeney, and Ioannis Paschalidis. "Adversarial Imitation Learning from Visual Observations using Latent Information." Transactions on Machine Learning Research.

The proposed projects can result in publications at top-notch machine learning venues (ICML, NeurIPS, ICLR, etc.). Therefore, we are looking for self-motivated undergraduate and graduate student volunteers who can dedicate sufficient time to meet the conference deadlines.

 

Interested students: Please fill out and follow the instructions on this form: https://docs.google.com/forms/d/e/1FAIpQLSeq_yN58oOFeWIsxrVfBVMDCkjhBoiHNFs0MeHBe_lW356-Hg/viewform

Last Updated: Oct 30, 2024 9:31 AM

Department of Computer Science, 305 N. University Street, West Lafayette, IN 47907

Purdue University Indianapolis, 723 W. Michigan St., Indianapolis, IN 46202

Phone: (765) 494-6010 • Fax: (765) 494-0739

Copyright © 2024 Purdue University | An equal access/equal opportunity university | Copyright Complaints | DOE Degree Scorecards

Trouble with this page? Accessibility issues? Please contact the College of Science.